Instructions to use TheMistoAI/MistoLine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TheMistoAI/MistoLine with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TheMistoAI/MistoLine", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
error when using diffusers
#5
by luluxxx - opened
hello i'm trying to use the controlnet with the example code given : but i get this error
OSError: TheMistoAI/MistoLine does not appear to have a file named diffusion_pytorch_model.bin
code:
controlnet_id = ControlNetModel.from_pretrained("TheMistoAI/MistoLine",torch_dtype=torch.float16)
We re-named the model file name for the diffusers..., please have a try...
Actually, as a convention to differentiate the full from the half precision models, in diffusers you use the fp16 variant, so the correct answer was to use:
controlnet = ControlNetModel.from_pretrained(
"TheMistoAI/MistoLine",
torch_dtype=torch.float16,
variant="fp16",
)
and not to change the model file name. For example this makes it so the people that uses the normal convention will get this error.
OSError: TheMistoAI/MistoLine does not appear to have a file named diffusion_pytorch_model.fp16.bin.
StrugglerXYH changed discussion status to closed